{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XSETP5XAKRWUIWDPVARNIG65KJ","short_pith_number":"pith:XSETP5XA","schema_version":"1.0","canonical_sha256":"bc8937f6e0546d44586fa822d41bdd525dd2feb6ee4ce7f1645800cd7fcdac4e","source":{"kind":"arxiv","id":"2312.03134","version":1},"attestation_state":"computed","paper":{"title":"A Hardware Evaluation Framework for Large Language Model Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.AR","authors_text":"August Ning, David Wentzlaff, Hengrui Zhang, Rohan Prabhakar","submitted_at":"2023-12-05T21:01:33Z","abstract_excerpt":"The past year has witnessed the increasing popularity of Large Language Models (LLMs). Their unprecedented scale and associated high hardware cost have impeded their broader adoption, calling for efficient hardware designs. With the large hardware needed to simply run LLM inference, evaluating different hardware designs becomes a new bottleneck.\n  This work introduces LLMCompass, a hardware evaluation framework for LLM inference workloads. LLMCompass is fast, accurate, versatile, and able to describe and evaluate different hardware designs. LLMCompass includes a mapper to automatically find pe"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.03134","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2023-12-05T21:01:33Z","cross_cats_sorted":["cs.DC","cs.LG"],"title_canon_sha256":"53be887290a16ffaa383f6a448734d0295ec6d677353c4e539f9f7f41d27990f","abstract_canon_sha256":"cd67350c29a741ea8a46f7aa13fb783abd9ba0ad1e95202b66fdcdb07db1d5fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:58.951207Z","signature_b64":"O078q77Pw8xBoZdC+TbOkCTdisunL7JHnOpAxDuqVM+vepaAWnwRbZ9H/S+FQxrD4WUx3ajM9PcWVWyYXRQ+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc8937f6e0546d44586fa822d41bdd525dd2feb6ee4ce7f1645800cd7fcdac4e","last_reissued_at":"2026-07-05T07:20:58.950733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:58.950733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Hardware Evaluation Framework for Large Language Model Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.AR","authors_text":"August Ning, David Wentzlaff, Hengrui Zhang, Rohan Prabhakar","submitted_at":"2023-12-05T21:01:33Z","abstract_excerpt":"The past year has witnessed the increasing popularity of Large Language Models (LLMs). Their unprecedented scale and associated high hardware cost have impeded their broader adoption, calling for efficient hardware designs. With the large hardware needed to simply run LLM inference, evaluating different hardware designs becomes a new bottleneck.\n  This work introduces LLMCompass, a hardware evaluation framework for LLM inference workloads. LLMCompass is fast, accurate, versatile, and able to describe and evaluate different hardware designs. LLMCompass includes a mapper to automatically find pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03134","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.03134/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.03134","created_at":"2026-07-05T07:20:58.950786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03134v1","created_at":"2026-07-05T07:20:58.950786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03134","created_at":"2026-07-05T07:20:58.950786+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSETP5XAKRWU","created_at":"2026-07-05T07:20:58.950786+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSETP5XAKRWUIWDP","created_at":"2026-07-05T07:20:58.950786+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSETP5XA","created_at":"2026-07-05T07:20:58.950786+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.05876","citing_title":"Think Before You Grid-Search: Floor-First Triage for LLM Serving","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2607.05876","citing_title":"Think Before You Grid-Search: Floor-First Triage for LLM Serving","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2504.09775","citing_title":"MIST: A Co-Design Framework for Heterogeneous, Multi-Stage LLM Inference","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00555","citing_title":"Sim-FA: A GPGPU Simulator Framework for Fine-Grained Asynchronous Pipeline Analysis","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16007","citing_title":"MemExplorer: Navigating the Heterogeneous Memory Design Space for Agentic Inference NPUs","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XSETP5XAKRWUIWDPVARNIG65KJ","json":"https://pith.science/pith/XSETP5XAKRWUIWDPVARNIG65KJ.json","graph_json":"https://pith.science/api/pith-number/XSETP5XAKRWUIWDPVARNIG65KJ/graph.json","events_json":"https://pith.science/api/pith-number/XSETP5XAKRWUIWDPVARNIG65KJ/events.json","paper":"https://pith.science/paper/XSETP5XA"},"agent_actions":{"view_html":"https://pith.science/pith/XSETP5XAKRWUIWDPVARNIG65KJ","download_json":"https://pith.science/pith/XSETP5XAKRWUIWDPVARNIG65KJ.json","view_paper":"https://pith.science/paper/XSETP5XA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03134&json=true","fetch_graph":"https://pith.science/api/pith-number/XSETP5XAKRWUIWDPVARNIG65KJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XSETP5XAKRWUIWDPVARNIG65KJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSETP5XAKRWUIWDPVARNIG65KJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSETP5XAKRWUIWDPVARNIG65KJ/action/storage_attestation","attest_author":"https://pith.science/pith/XSETP5XAKRWUIWDPVARNIG65KJ/action/author_attestation","sign_citation":"https://pith.science/pith/XSETP5XAKRWUIWDPVARNIG65KJ/action/citation_signature","submit_replication":"https://pith.science/pith/XSETP5XAKRWUIWDPVARNIG65KJ/action/replication_record"}},"created_at":"2026-07-05T07:20:58.950786+00:00","updated_at":"2026-07-05T07:20:58.950786+00:00"}